Rework the unused ALL_PROXIES list into util/proxy_pool.rs: - hourly sweep of the public lists, TLS-verified cloudflare trace checks, >=2 successes with a median under 1.5s, one proxy per exit IP; proxies that show our own IP are dropped, two failures in a row evict - per-site sets checked against a site URL (rule34video: robots.txt), round-robin, 10-min per-site cooldown on 429/challenge pages, live request outcomes fed back - started from main (PROXY_POOL=0 disables; PROXY_POOL_LISTS, PROXY_POOL_CONCURRENCY), /api/proxies shows its status without credentials - wreq "socks" feature enabled: SOCKS proxies silently failed before rule34video enrichment is back, through the pool: full detail pages (1080p..360p formats, tags, artist), 8 concurrent, one 4s deadline per listing; late pages keep running and land in the 2h detail cache, which cached listings are re-merged with on every serve. No ready proxies means no enrichment (no direct fallback). Requester::get_via sends a pooled request with certificate checks, sharing the session's cookie jar. Also adds an ignored live probe showing /embed/ shares the 429 limit. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AEp724zDpCWNaSeCrMSvjx
130 lines
3.7 KiB
Rust
130 lines
3.7 KiB
Rust
use std::fmt;
|
|
use std::str::FromStr;
|
|
|
|
use serde::Serialize;
|
|
use url::Url;
|
|
use wreq::Proxy as WreqProxy;
|
|
|
|
#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
|
|
pub struct Proxy {
|
|
pub protocol: String,
|
|
pub host: String,
|
|
pub port: u16,
|
|
pub username: Option<String>,
|
|
pub password: Option<String>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, PartialEq, Eq)]
|
|
pub struct ProxyParseError {
|
|
message: String,
|
|
}
|
|
|
|
impl ProxyParseError {
|
|
fn new(message: impl Into<String>) -> Self {
|
|
Self {
|
|
message: message.into(),
|
|
}
|
|
}
|
|
}
|
|
|
|
impl fmt::Display for ProxyParseError {
|
|
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
|
|
write!(f, "{}", self.message)
|
|
}
|
|
}
|
|
|
|
impl std::error::Error for ProxyParseError {}
|
|
|
|
impl fmt::Display for Proxy {
|
|
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
|
|
match (&self.username, &self.password) {
|
|
(Some(username), Some(password)) => write!(
|
|
f,
|
|
"{}://{}:{}@{}:{}",
|
|
self.protocol, username, password, self.host, self.port
|
|
),
|
|
(Some(username), None) => write!(
|
|
f,
|
|
"{}://{}@{}:{}",
|
|
self.protocol, username, self.host, self.port
|
|
),
|
|
(None, Some(_)) => write!(f, "{}://{}:{}", self.protocol, self.host, self.port),
|
|
(None, None) => write!(f, "{}://{}:{}", self.protocol, self.host, self.port),
|
|
}
|
|
}
|
|
}
|
|
|
|
impl Proxy {
|
|
/// `protocol://host:port`, without credentials: safe to show or log.
|
|
pub fn redacted(&self) -> String {
|
|
format!("{}://{}:{}", self.protocol, self.host, self.port)
|
|
}
|
|
|
|
pub fn parse(input: &str) -> Result<Self, ProxyParseError> {
|
|
input.parse()
|
|
}
|
|
|
|
pub fn to_wreq_proxy(&self) -> Result<WreqProxy, ProxyParseError> {
|
|
let base_url = format!("{}://{}:{}", self.protocol, self.host, self.port);
|
|
let proxy_url = Url::parse(&base_url)
|
|
.map_err(|e| ProxyParseError::new(format!("invalid proxy url: {e}")))?;
|
|
|
|
let mut proxy = WreqProxy::all(proxy_url.as_str())
|
|
.map_err(|e| ProxyParseError::new(format!("failed to build wreq proxy: {e}")))?;
|
|
|
|
if let Some(username) = &self.username {
|
|
let password = self.password.as_deref().unwrap_or("");
|
|
proxy = proxy.basic_auth(username, password);
|
|
}
|
|
|
|
Ok(proxy)
|
|
}
|
|
}
|
|
|
|
impl FromStr for Proxy {
|
|
type Err = ProxyParseError;
|
|
|
|
fn from_str(input: &str) -> Result<Self, Self::Err> {
|
|
let trimmed = input.trim();
|
|
if trimmed.is_empty() {
|
|
return Err(ProxyParseError::new("proxy string is empty"));
|
|
}
|
|
|
|
let with_scheme = if trimmed.contains("://") {
|
|
trimmed.to_string()
|
|
} else {
|
|
format!("http://{trimmed}")
|
|
};
|
|
|
|
let url = Url::parse(&with_scheme)
|
|
.map_err(|e| ProxyParseError::new(format!("invalid proxy url: {e}")))?;
|
|
if !(url.path().is_empty() || url.path() == "/")
|
|
|| url.query().is_some()
|
|
|| url.fragment().is_some()
|
|
{
|
|
return Err(ProxyParseError::new(format!(
|
|
"proxy url must not include path, query, or fragment: {:?}",
|
|
input
|
|
)));
|
|
}
|
|
|
|
let host = url
|
|
.host_str()
|
|
.ok_or_else(|| ProxyParseError::new("proxy url is missing host"))?
|
|
.to_string();
|
|
|
|
let port = url.port().unwrap_or(80);
|
|
|
|
Ok(Proxy {
|
|
protocol: url.scheme().to_string(),
|
|
host,
|
|
port,
|
|
username: match url.username() {
|
|
"" => None,
|
|
username => Some(username.to_string()),
|
|
},
|
|
password: url.password().map(|password| password.to_string()),
|
|
})
|
|
}
|
|
}
|